Build with AI agents in Netlify
Start new projects or improve existing ones with agents running on production infrastructure from the first prompt.
Claude Agent Claude Agent is working 3s
Prompt. Review. Ship.
Open your project, describe what you need, and run. No setup required.
Agents that know your project
Locally, an agent knows your code. On Netlify, it knows your code and your environment — so it can get it right the first time.
That context lets it wire up a serverless function, configure auth, or set up a form without extra setup.
Project context available from first prompt
- Code
- Environment variables
- Build settings
- Deployment pipeline
- Netlify primitives
With Agent Runners, you can literally say, 'Whatever I did last broke the site—can you investigate, fix it, and send me a preview?' and it would do it. That's not the future; that's the present.
Your team stays in control
The same role-based access that governs your deployments controls who can run agents—so you can extend AI development across your business without extending risk. Every change is tracked, reversible, and auditable.
Track exactly who prompted what, when.
Internal Builders can propose changes, Developers control deployment.
Run agents in isolated environments that never touch secrets.
Integrate with your existing Git workflow.
Roll back to any previous version in one click.
Review every update with a production-matching preview.
Plenty of AI coding assistants write code. The real challenge is validating it in an environment that matches production. Netlify changed that — no surprises at deploy, staging delays, or production-only bugs.
Start running
Agent Runners runs on production infrastructure from the first prompt. Here’s where to go next.